Search results for: feature noise

Authors: Radhika Ranjan Roy

Abstract:

Deployment of machine learning (ML)/deep learning (DL) algorithms for cyberattack detection in operational communications networks (wireless and/or wire-line) is being delayed because of low-performance parameters (e.g., recall, precision, and f₁-score). If datasets become imbalanced, which is the usual case for communications networks, the performance tends to become worse. Complexities in handling reducing dimensions of the feature sets for increasing performance are also a huge problem. Mahalanobis algorithms have been widely applied in scientific research because Mahalanobis distance metric learning is a successful framework. In this paper, we have investigated the Mahalanobis binary classifier algorithm for increasing cyberattack detection performance over communications networks as a proof of concept. We have also found that high-dimensional information in intermediate features that are not utilized as much for classification tasks in ML/DL algorithms are the main contributor to the state-of-the-art of improved performance of the Mahalanobis method, even for imbalanced and sparse datasets. With no feature reduction, MD offers uniform results for precision, recall, and f₁-score for unbalanced and sparse NSL-KDD datasets.

Keywords: Mahalanobis distance, machine learning, deep learning, NS-KDD, local intrinsic dimensionality, chi-square, positive semi-definite, area under the curve

Procedia PDF Downloads 59

Authors: Sky Chou, Joseph C. Chen

Abstract:

This paper focuses on using Six Sigma methodologies to improve the surface roughness of a manufactured part produced by the CNC milling machine. It presents a case study where the surface roughness of milled aluminum is required to reduce or eliminate defects and to improve the process capability index C_p and C_pk for a CNC milling process. The six sigma methodology, DMAIC (design, measure, analyze, improve, and control) approach, was applied in this study to improve the process, reduce defects, and ultimately reduce costs. The Taguchi-based six sigma approach was applied to identify the optimized processing parameters that led to the targeted surface roughness specified by our customer. A L₉ orthogonal array was applied in the Taguchi experimental design, with four controllable factors and one non-controllable/noise factor. The four controllable factors identified consist of feed rate, depth of cut, spindle speed, and surface roughness. The noise factor is the difference between the old cutting tool and the new cutting tool. The confirmation run with the optimal parameters confirmed that the new parameter settings are correct. The new settings also improved the process capability index. The purpose of this study is that the Taguchi–based six sigma approach can be efficiently used to phase out defects and improve the process capability index of the CNC milling process.

Keywords: CNC machining, six sigma, surface roughness, Taguchi methodology

Procedia PDF Downloads 230

Authors: Esther Van Andel, Stefanie C. Lange, Maarten M. J. Smulders, Han Zuilhof

Abstract:

False outcomes of diagnostic tests are a major concern in medical health care. To improve the reliability of surface-based diagnostic tests, it is of crucial importance to diminish background signals that arise from the non-specific binding of biomolecules, a process called fouling. The aim is to create surfaces that repel all biomolecules except the molecule of interest. This can be achieved by incorporating antifouling protein repellent coatings in between the sensor surface and it’s recognition elements (e.g. antibodies, sugars, aptamers). Zwitterionic polymer brushes are considered excellent antifouling materials, however, to be able to bind the molecule of interest, the polymer brushes have to be functionalized and so far this was only achieved at the expense of either antifouling or binding capacity. To overcome this limitation, we combined both features into one single monomer: a zwitterionic sulfobetaine, ensuring antifouling capabilities, equipped with a clickable azide moiety which allows for further functionalization. By copolymerizing this monomer together with a standard sulfobetaine, the number of azides (and with that the number of recognition elements) can be tuned depending on the application. First, the clickable azido-monomer was synthesized and characterized, followed by copolymerizing this monomer to yield functionalizable antifouling brushes. The brushes were fully characterized using surface characterization techniques like XPS, contact angle measurements, G-ATR-FTIR and XRR. As a proof of principle, the brushes were subsequently functionalized with biotin via strain-promoted alkyne azide click reactions, which yielded a fully zwitterionic biotin-containing 3D-functionalized coating. The sensing capacity was evaluated by reflectometry using avidin and fibrinogen containing protein solutions. The surfaces showed excellent antifouling properties as illustrated by the complete absence of non-specific fibrinogen binding, while at the same time clear responses were seen for the specific binding of avidin. A great increase in signal-to-noise ratio was observed, even when the amount of functional groups was lowered to 1%, compared to traditional modification of sulfobetaine brushes that rely on a 2D-approach in which only the top-layer can be functionalized. This study was performed on stoichiometric silicon nitride surfaces for future microring resonator based assays, however, this methodology can be transferred to other biosensor platforms which are currently being investigated. The approach presented herein enables a highly efficient strategy for selective binding with retained antifouling properties for improved signal-to-noise ratios in binding assays. The number of recognition units can be adjusted to a specific need, e.g. depending on the size of the analyte to be bound, widening the scope of these functionalizable surface coatings.

Keywords: antifouling, signal-to-noise ratio, surface functionalization, zwitterionic polymer brushes

Procedia PDF Downloads 291

Authors: J. M. Mayoral, M. Anaya

Abstract:

The urban and economic development of cities demands the construction of water use and flood control infrastructure. Likewise, it is necessary to determine the safety level of the structures built with the current standards and if it is necessary to define the reinforcement actions. The foregoing is even more important in structures of great importance, such as dams, since they imply a greater risk for the population in case of failure or undesirable operating conditions (e.g., seepage, cracks, subsidence). This article presents a methodology for determining the seismic integrity of dams in urban areas. From direct measurements of the dynamic properties using geophysical exploration and ambient seismic noise measurements, the seismic integrity of the concrete-faced rockfill dam selected as a case of study is evaluated. To validate the results, two accelerometer stations were installed (e.g., free field and crest of the dam). Once the dynamic properties were determined, three-dimensional finite difference models were developed to evaluate the dam seismic performance for different intensities of movement, considering the site response and soil-structure interaction effects. The seismic environment was determined from the uniform hazard spectra for several return periods. Based on the results obtained, the safety level of the dam against different seismic actions was determined, and the effectiveness of ambient seismic noise measurements in dynamic characterization and subsequent evaluation of the seismic integrity of urban dams was evaluated.

Keywords: risk, seismic, soil-structure interaction, urban dams

Procedia PDF Downloads 91

Authors: V. Saccà, A. Sarica, F. Novellino, S. Barone, T. Tallarico, E. Filippelli, A. Granata, P. Valentino, A. Quattrone

Abstract:

The work aim was to evaluate how well Random Forest (RF) and Support Vector Machine (SVM) algorithms could support the early diagnosis of Multiple Sclerosis (MS) from resting-state functional connectivity data. In particular, we wanted to explore the ability in distinguishing between controls and patients of mean signals extracted from ICA components corresponding to 15 well-known networks. Eighteen patients with early-MS (mean-age 37.42±8.11, 9 females) were recruited according to McDonald and Polman, and matched for demographic variables with 19 healthy controls (mean-age 37.55±14.76, 10 females). MRI was acquired by a 3T scanner with 8-channel head coil: (a)whole-brain T1-weighted; (b)conventional T2-weighted; (c)resting-state functional MRI (rsFMRI), 200 volumes. Estimated total lesion load (ml) and number of lesions were calculated using LST-toolbox from the corrected T1 and FLAIR. All rsFMRIs were pre-processed using tools from the FMRIB's Software Library as follows: (1) discarding of the first 5 volumes to remove T1 equilibrium effects, (2) skull-stripping of images, (3) motion and slice-time correction, (4) denoising with high-pass temporal filter (128s), (5) spatial smoothing with a Gaussian kernel of FWHM 8mm. No statistical significant differences (t-test, p < 0.05) were found between the two groups in the mean Euclidian distance and the mean Euler angle. WM and CSF signal together with 6 motion parameters were regressed out from the time series. We applied an independent component analysis (ICA) with the GIFT-toolbox using the Infomax approach with number of components=21. Fifteen mean components were visually identified by two experts. The resulting z-score maps were thresholded and binarized to extract the mean signal of the 15 networks for each subject. Statistical and machine learning analysis were then conducted on this dataset composed of 37 rows (subjects) and 15 features (mean signal in the network) with R language. The dataset was randomly splitted into training (75%) and test sets and two different classifiers were trained: RF and RBF-SVM. We used the intrinsic feature selection of RF, based on the Gini index, and recursive feature elimination (rfe) for the SVM, to obtain a rank of the most predictive variables. Thus, we built two new classifiers only on the most important features and we evaluated the accuracies (with and without feature selection) on test-set. The classifiers, trained on all the features, showed very poor accuracies on training (RF:58.62%, SVM:65.52%) and test sets (RF:62.5%, SVM:50%). Interestingly, when feature selection by RF and rfe-SVM were performed, the most important variable was the sensori-motor network I in both cases. Indeed, with only this network, RF and SVM classifiers reached an accuracy of 87.5% on test-set. More interestingly, the only misclassified patient resulted to have the lowest value of lesion volume. We showed that, with two different classification algorithms and feature selection approaches, the best discriminant network between controls and early MS, was the sensori-motor I. Similar importance values were obtained for the sensori-motor II, cerebellum and working memory networks. These findings, in according to the early manifestation of motor/sensorial deficits in MS, could represent an encouraging step toward the translation to the clinical diagnosis and prognosis.

Keywords: feature selection, machine learning, multiple sclerosis, random forest, support vector machine

Procedia PDF Downloads 226

Authors: Abdullah Alnutayfat, Alexander Sutin, Dong Liu

Abstract:

Wind turbine has become one of the most popular energy productions. However, failure of blades and maintenance costs evolve into significant issues in the wind power industry, so it is essential to detect the initial blade defects to avoid the collapse of the blades and structure. This paper aims to apply modulation of high-frequency blade vibrations by low-frequency blade rotation, which is close to the known Vibro-Acoustic Modulation (VAM) method. The high-frequency wideband blade vibration is produced by the interaction of the surface blades with the environment air turbulence, and the low-frequency modulation is produced by alternating bending stress due to gravity. The low-frequency load of rotational wind turbine blades ranges between 0.2-0.4 Hz and can reach up to 2 Hz for strong wind. The main difference between this study and previous ones on VAM methods is the use of a wideband vibration signal from the blade's natural vibrations. Different features of the vibroacoustic modulation are considered using a simple model of breathing crack. This model considers the simple mechanical oscillator, where the parameters of the oscillator are varied due to low-frequency blade rotation. During the blade's operation, the internal stress caused by the weight of the blade modifies the crack's elasticity and damping. The laboratory experiment using steel samples demonstrates the possibility of VAM using a probe wideband noise signal. A cycle load with a small amplitude was used as a pump wave to damage the tested sample, and a small transducer generated a wideband probe wave. The received signal demodulation was conducted using the Detecting of Envelope Modulation on Noise (DEMON) approach. In addition, the experimental results were compared with the modulation index (MI) technique regarding the harmonic pump wave. The wideband and traditional VAM methods demonstrated similar sensitivity for earlier detection of invisible cracks. Importantly, employing a wideband probe signal with the DEMON approach speeds up and simplifies testing since it eliminates the need to conduct tests repeatedly for various harmonic probe frequencies and to adjust the probe frequency.

Keywords: vibro-acoustic modulation, detecting of envelope modulation on noise, damage, turbine blades

Procedia PDF Downloads 84

Authors: Wade Ghribi, Abdelmoty M. Ahmed, Ahmed Said Badawy, Belgacem Bouallegue

Abstract:

In higher education institutions, the most pressing priority is to improve student performance and retention. Large volumes of student data are used in Educational Data Mining techniques to find new hidden information from students' learning behavior, particularly to uncover the early symptom of at-risk pupils. On the other hand, data with noise, outliers, and irrelevant information may provide incorrect conclusions. By identifying features of students' data that have the potential to improve performance prediction results, comparing and identifying the most appropriate ensemble learning technique after preprocessing the data, and optimizing the hyperparameters, this paper aims to develop a reliable students' performance prediction model for Higher Education Institutions. Data was gathered from two different systems: a student information system and an e-learning system for undergraduate students in the College of Computer Science of a Saudi Arabian State University. The cases of 4413 students were used in this article. The process includes data collection, data integration, data preprocessing (such as cleaning, normalization, and transformation), feature selection, pattern extraction, and, finally, model optimization and assessment. Random Forest, Bagging, Stacking, Majority Vote, and two types of Boosting techniques, AdaBoost and XGBoost, are ensemble learning approaches, whereas Decision Tree, Support Vector Machine, and Artificial Neural Network are supervised learning techniques. Hyperparameters for ensemble learning systems will be fine-tuned to provide enhanced performance and optimal output. The findings imply that combining features of students' behavior from e-learning and students' information systems using Majority Vote produced better outcomes than the other ensemble techniques.

Keywords: educational data mining, student performance prediction, e-learning, classification, ensemble learning, higher education

Procedia PDF Downloads 90

Authors: Sandeep Santosh, O. P. Sahu

Abstract:

In this paper, performance comparison of wideband covariance matrix sparse representation (W-CMSR) method with other existing wideband Direction of Arrival (DOA) estimation methods has been made.W-CMSR relies less on a priori information of the incident signal number than the ordinary subspace based methods.Consider the perturbation free covariance matrix of the wideband array output. The diagonal covariance elements are contaminated by unknown noise variance. The covariance matrix of array output is conjugate symmetric i.e its upper right triangular elements can be represented by lower left triangular ones.As the main diagonal elements are contaminated by unknown noise variance,slide over them and align the lower left triangular elements column by column to obtain a measurement vector.Simulation results for W-CMSR are compared with simulation results of other wideband DOA estimation methods like Coherent signal subspace method (CSSM), Capon, l1-SVD, and JLZA-DOA. W-CMSR separate two signals very clearly and CSSM, Capon, L1-SVD and JLZA-DOA fail to separate two signals clearly and an amount of pseudo peaks exist in the spectrum of L1-SVD.

Keywords: W-CMSR, wideband direction of arrival (DOA), covariance matrix, electrical and computer engineering

Procedia PDF Downloads 453

Authors: S. Nandagopalan, N. Pradeep

Abstract:

The aim of this paper is to propose a general framework for storing, analyzing, and extracting knowledge from two-dimensional echocardiographic images, color Doppler images, non-medical images, and general data sets. A number of high performance data mining algorithms have been used to carry out this task. Our framework encompasses four layers namely physical storage, object identification, knowledge discovery, user level. Techniques such as active contour model to identify the cardiac chambers, pixel classification to segment the color Doppler echo image, universal model for image retrieval, Bayesian method for classification, parallel algorithms for image segmentation, etc., were employed. Using the feature vector database that have been efficiently constructed, one can perform various data mining tasks like clustering, classification, etc. with efficient algorithms along with image mining given a query image. All these facilities are included in the framework that is supported by state-of-the-art user interface (UI). The algorithms were tested with actual patient data and Coral image database and the results show that their performance is better than the results reported already.

Keywords: active contour, bayesian, echocardiographic image, feature vector

Procedia PDF Downloads 403

Authors: Sky Chou, Joseph C. Chen

Abstract:

This paper focuses on using six sigma methodologies to reach the desired shrinkage of a manufactured high-density polyurethane (HDPE) part produced by the injection molding machine. It presents a case study where the correct shrinkage is required to reduce or eliminate defects and to improve the process capability index Cp and Cpk for an injection molding process. To improve this process and keep the product within specifications, the six sigma methodology, design, measure, analyze, improve, and control (DMAIC) approach, was implemented in this study. The six sigma approach was paired with the Taguchi methodology to identify the optimized processing parameters that keep the shrinkage rate within the specifications by our customer. An L9 orthogonal array was applied in the Taguchi experimental design, with four controllable factors and one non-controllable/noise factor. The four controllable factors identified consist of the cooling time, melt temperature, holding time, and metering stroke. The noise factor is the difference between material brand 1 and material brand 2. After the confirmation run was completed, measurements verify that the new parameter settings are optimal. With the new settings, the process capability index has improved dramatically. The purpose of this study is to show that the six sigma and Taguchi methodology can be efficiently used to determine important factors that will improve the process capability index of the injection molding process.

Keywords: injection molding, shrinkage, six sigma, Taguchi parameter design

Procedia PDF Downloads 157

Authors: Hala Zaghloul, Taymoor Nazmy

Abstract:

One of the great challenges of the 21st century is to build a robot that can perceive and act within its environment and communicate with people, while also exhibiting the cognitive capabilities that lead to performance like that of people. The Pulse Coupled Neural Network, PCNN, is a relative new ANN model that derived from a neural mammal model with a great potential in the area of image processing as well as target recognition, feature extraction, speech recognition, combinatorial optimization, compressed encoding. PCNN has unique feature among other types of neural network, which make it a candid to be an important approach for perceiving in cognitive systems. This work show and emphasis on the potentials of PCNN to perform different tasks related to image processing. The main drawback or the obstacle that prevent the direct implementation of such technique, is the need to find away to control the PCNN parameters toward perform a specific task. This paper will evaluate the performance of PCNN standard model for processing images with different properties, and select the important parameters that give a significant result, also, the approaches towards find a way for the adaptation of the PCNN parameters to perform a specific task.

Keywords: cognitive system, image processing, segmentation, PCNN kernels

Procedia PDF Downloads 260

Authors: Pamir Gogoi, Ratree Wayland

Abstract:

This study investigates the acoustic measures of breathiness when coarticulated with nasality. The acoustic correlates of breathiness and nasality that has already been well established after years of empirical research. Some of these acoustic parameters - like low frequency peaks and wider bandwidths- are common for both nasal and breathy voice. Therefore, it is likely that these parameters interact when a sound is coarticulated with breathiness and nasality. This leads to the hypothesis that the acoustic parameters, which usually act as robust cues in differentiating between breathy and modal voice, might not be reliable cues for differentiating between breathy and modal voice when breathiness is coarticulated with nasality. The effect of nasality on the perception of breathiness has been explored in earlier studies using synthesized speech. The results showed that perceptually, nasality and breathiness do interact. The current study investigates if a similar pattern is observed in natural speech. The study is conducted on Marathi, an Indo-Aryan language which has a three-way contrast between nasality and breathiness. That is, there is a phonemic distinction between nasals, breathy voice and breathy-nasals. Voice quality parameters like – H1-H2 (Difference between the amplitude of first and second harmonic), H1-A3 (Difference between the amplitude of first harmonic and third formant, CPP (Cepstral Peak Prominence), HNR (Harmonics to Noise ratio) and B1 (Bandwidth of first formant) were extracted. Statistical models like linear mixed effects regression and Random Forest classifiers show that measures that capture the noise component in the signal- like CPP and HNR- can classify breathy voice from modal voice better than spectral measures when breathy voice is coarticulated with nasality.

Keywords: breathiness, marathi, nasality, voice quality

Procedia PDF Downloads 73

Authors: Vinod Ponnagandla, Brenton McLaury, Siamack Shirazi

Abstract:

Sand production can lead to deposition of particles or erosion. Low production rates resulting in deposition can partially clog systems and cause under deposit corrosion. Commercially available nonintrusive acoustic sand detectors are attractive as they claim to detect sand production. Acoustic sand detectors are used during oil and gas production; however, operators often do not know the threshold detection limits of these devices. It is imperative to know the detection limits to appropriately plan for cleaning of separation equipment or examine risk of erosion. These monitors are based on detecting the acoustic signature of sand as the particles impact the pipe walls. The objective of this work is to determine threshold detection limits for acoustic sand monitors that are commercially available. The minimum threshold sand concentration that can be detected in a pipe are determined as a function of flowing gas and liquid velocities. A large scale flow loop with a 4-inch test section is utilized. Commercially available sand monitors (ClampOn and Roxar) are evaluated for different flow regimes, sand sizes and pipe orientation (vertical and horizontal). The manufacturers’ recommend that the monitors be placed on a bend to maximize the number of particle impacts, so results are shown for monitors placed at 45 and 90 degree positions in a bend. Acoustic sand monitors that clamp to the outside of pipe are passive and listen for solid particle impact noise. The threshold sand rate is calculated by eliminating the background noise created by the flow of gas and liquid in the pipe for various flow regimes that are generated in horizontal and vertical test sections. The average sand sizes examined are 150 and 300 microns. For stratified and bubbly flows the threshold sand rates are much higher than other flow regimes such as slug and annular flow regimes that are investigated. However, the background noise generated by slug flow regime is very high and cause a high uncertainty in detection limits. The threshold sand rates for annular flow and dry gas conditions are the lowest because of high gas velocities. The effects of monitor placement around elbows that are in vertical and horizontal pipes are also examined for 150 micron. The results show that the threshold sand rates that are detected in vertical orientation are generally lower for all various flow regimes that are investigated.

Keywords: acoustic monitor, sand, multiphase flow, threshold

Procedia PDF Downloads 384

Authors: Hao Wang, Shengchun Wang, Weidong Wang

Abstract:

On the influence of train vibration and environmental noise on the measurement of track wear, we proposed a method for automatic extraction of circular arc on the inner or outer side of the rail waist and achieved the high-precision registration of rail profile. Firstly, a polynomial fitting method based on truncated residual histogram was proposed to find the optimal fitting curve of the profile and reduce the influence of noise on profile curve fitting. Then, based on the curvature distribution characteristics of the fitting curve, the interval search algorithm based on dynamic window’s maximum curvature entropy was proposed to realize the automatic segmentation of small circular arc. At last, we fit two circle centers as matching reference points based on small circular arcs on both sides and realized the alignment from the measured profile to the standard designed profile. The static experimental results show that the mean and standard deviation of the method are controlled within 0.01mm with small measurement errors and high repeatability. The dynamic test also verified the repeatability of the method in the train-running environment, and the dynamic measurement deviation of rail wear is within 0.2mm with high repeatability.

Keywords: curvature entropy, profile registration, rail wear, structured light, train-running

Procedia PDF Downloads 243

Authors: Mattias Bergstrom

Abstract:

Significance of the Study: This research will provide new insights into the risks with digital embedded infrastructure. Through this research, we will analyze each risk and its potential negation strategies, especially for AI and autonomous automation. Moreover, the analysis that is presented in this paper will convey valuable information for future research that can create more stable, secure, and efficient autonomous systems. To learn and understand the risks, a large IoT system was envisioned, and risks with hardware, tampering, and cyberattacks were collected, researched, and evaluated to create a comprehensive understanding of the potential risks. Potential solutions have then been evaluated on an open source IoT hardware setup. This list shows the identified passive and active risks evaluated in the research. Passive Risks: (1) Hardware failures- Critical Systems relying on high rate data and data quality are growing; SCADA systems for infrastructure are good examples of such systems. (2) Hardware delivers erroneous data- Sensors break, and when they do so, they don’t always go silent; they can keep going, just that the data they deliver is garbage, and if that data is not filtered out, it becomes disruptive noise in the system. (3) Bad Hardware injection- Erroneous generated sensor data can be pumped into a system by malicious actors with the intent to create disruptive noise in critical systems. (4) Data gravity- The weight of the data collected will affect Data-Mobility. (5) Cost inhibitors- Running services that need huge centralized computing is cost inhibiting. Large complex AI can be extremely expensive to run. Active Risks: Denial of Service- It is one of the most simple attacks, where an attacker just overloads the system with bogus requests so that valid requests disappear in the noise. Malware- Malware can be anything from simple viruses to complex botnets created with specific goals, where the creator is stealing computer power and bandwidth from you to attack someone else. Ransomware- It is a kind of malware, but it is so different in its implementation that it is worth its own mention. The goal with these pieces of software is to encrypt your system so that it can only be unlocked with a key that is held for ransom. DNS spoofing- By spoofing DNS calls, valid requests and data dumps can be sent to bad destinations, where the data can be extracted for extortion or to corrupt and re-inject into a running system creating a data echo noise loop. After testing multiple potential solutions. We found that the most prominent solution to these risks was to use a Peer 2 Peer consensus algorithm over a blockchain to validate the data and behavior of the devices (sensors, storage, and computing) in the system. By the devices autonomously policing themselves for deviant behavior, all risks listed above can be negated. In conclusion, an Internet middleware that provides these features would be an easy and secure solution to any future autonomous IoT deployments. As it provides separation from the open Internet, at the same time, it is accessible over the blockchain keys.

Keywords: IoT, security, infrastructure, SCADA, blockchain, AI

Procedia PDF Downloads 87

Authors: Chandra Gupt Porwal

Abstract:

Excessive vibration means increased wear, increased repair efforts, bad product selection & quality and high energy consumption. This may be sometimes experienced by cavitation or suction/discharge re-circulation which could occur only when net positive suction head available NPSHA drops below the net positive suction head required NPSHR. Cavitation can cause axial surging if it is excessive, will damage mechanical seals, bearings, possibly other pump components frequently and shorten the life of the impeller. Efforts have been made to explain Suction Energy (SE), Specific Speed (Ns), Suction Specific Speed (Nss), NPSHA, NPSHR & their significance, possible reasons of cavitation /internal re-circulation, its diagnostics and remedial measures to arrest and prevent cavitation in this paper. A case study is presented by the author highlighting that the root cause of unwanted noise and vibration is due to cavitation, caused by high specific speeds or inadequate net- positive suction head available which results in damages to material surfaces of impeller & suction bells and degradation of machine performance, its capacity and efficiency too. The author strongly recommends revisiting the technical specifications of CW pumps to provide sufficient NPSH margin ratios > 1.5, for future projects and Nss be limited to 8500 -9000 for cavitation free operation.

Keywords: best efficiency point (BEP), net positive suction head NPSHA, NPSHR, specific speed NS, suction specific speed NSS

Procedia PDF Downloads 241

Authors: Rajpal Kaur, Pooja Choudhary

Abstract:

Biometrics, which refers to identifying an individual based on his or her physiological or behavioral characteristics, has the capabilities to the reliably distinguish between an authorized person and an imposter. The Signature recognition systems can categorized as offline (static) and online (dynamic). This paper presents Surf Feature based recognition of offline signatures system that is trained with low-resolution scanned signature images. The signature of a person is an important biometric attribute of a human being which can be used to authenticate human identity. However the signatures of human can be handled as an image and recognized using computer vision and HMM techniques. With modern computers, there is need to develop fast algorithms for signature recognition. There are multiple techniques are defined to signature recognition with a lot of scope of research. In this paper, (static signature) off-line signature recognition & verification using surf feature with HMM is proposed, where the signature is captured and presented to the user in an image format. Signatures are verified depended on parameters extracted from the signature using various image processing techniques. The Off-line Signature Verification and Recognition is implemented using Mat lab platform. This work has been analyzed or tested and found suitable for its purpose or result. The proposed method performs better than the other recently proposed methods.

Keywords: offline signature verification, offline signature recognition, signatures, SURF features, HMM

Procedia PDF Downloads 365

Authors: Naser Safdarian, Nader Jafarnia Dabanloo

Abstract:

In this paper we used four features i.e. Q-wave integral, QRS complex integral, T-wave integral and total integral as extracted feature from normal and patient ECG signals to detection and localization of myocardial infarction (MI) in left ventricle of heart. In our research we focused on detection and localization of MI in standard ECG. We use the Q-wave integral and T-wave integral because this feature is important impression in detection of MI. We used some pattern recognition method such as Artificial Neural Network (ANN) to detect and localize the MI. Because these methods have good accuracy for classification of normal and abnormal signals. We used one type of Radial Basis Function (RBF) that called Probabilistic Neural Network (PNN) because of its nonlinearity property, and used other classifier such as k-Nearest Neighbors (KNN), Multilayer Perceptron (MLP) and Naive Bayes Classification. We used PhysioNet database as our training and test data. We reached over 80% for accuracy in test data for localization and over 95% for detection of MI. Main advantages of our method are simplicity and its good accuracy. Also we can improve accuracy of classification by adding more features in this method. A simple method based on using only four features which extracted from standard ECG is presented which has good accuracy in MI localization.

Keywords: ECG signal processing, myocardial infarction, features extraction, pattern recognition

Procedia PDF Downloads 439

Authors: Kay Thinzar Phu, Lwin Lwin Oo

Abstract:

In an intelligent transport system and advanced driver assistance system, the developing of real-time traffic sign detection and recognition (TSDR) system plays an important part in recent research field. There are many challenges for developing real-time TSDR system due to motion artifacts, variable lighting and weather conditions and situations of traffic signs. Researchers have already proposed various methods to minimize the challenges problem. The aim of the proposed research is to develop an efficient and effective TSDR in real time. This system proposes an adaptive thresholding method based on RGB color for traffic signs detection and new features for traffic signs recognition. In this system, the RGB color thresholding is used to detect the blue and yellow color traffic signs regions. The system performs the shape identify to decide whether the output candidate region is traffic sign or not. Lastly, new features such as termination points, bifurcation points, and 90’ angles are extracted from validated image. This system uses Myanmar Traffic Sign dataset.

Keywords: adaptive thresholding based on RGB color, blue color detection, feature extraction, yellow color detection

Procedia PDF Downloads 284

Authors: Jamshaid Ul Rahman, Faiza Makhdoom, Dianchen Lu

Abstract:

Activation functions play a decisive role in determining the capacity of Deep Neural Networks (DNNs) as they enable neural networks to capture inherent nonlinearities present in data fed to them. The prior research on activation functions primarily focused on the utility of monotonic or non-oscillatory functions, until Growing Cosine Unit (GCU) broke the taboo for a number of applications. In this paper, a Convolutional Neural Network (CNN) model named as ASU-CNN is proposed which utilizes recently designed activation function ASU across its layers. The effect of this non-monotonic and oscillatory function is inspected through feature map visualizations from different convolutional layers. The optimization of proposed network is offered by Adam with a fine-tuned adjustment of learning rate. The network achieved promising results on both training and testing data for the classification of CIFAR-10. The experimental results affirm the computational feasibility and efficacy of the proposed model for performing tasks related to the field of computer vision.

Keywords: amplifying sine unit, activation function, convolutional neural networks, oscillatory activation, image classification, CIFAR-10

Procedia PDF Downloads 85

Authors: Alla Levina, Sergey Taranov

Abstract:

The classical approach to the providing noise immunity and integrity of information that process in computing devices and communication channels is to use linear codes. Linear codes have fast and efficient algorithms of encoding and decoding information, but this codes concentrate their detect and correct abilities in certain error configurations. To protect against any configuration of errors at predetermined probability can robust codes. This is accomplished by the use of perfect nonlinear and almost perfect nonlinear functions to calculate the code redundancy. The paper presents the error-correcting coding scheme using biorthogonal wavelet transform. Wavelet transform applied in various fields of science. Some of the wavelet applications are cleaning of signal from noise, data compression, spectral analysis of the signal components. The article suggests methods for constructing linear codes based on wavelet decomposition. For developed constructions we build generator and check matrix that contain the scaling function coefficients of wavelet. Based on linear wavelet codes we develop robust codes that provide uniform protection against all errors. In article we propose two constructions of robust code. The first class of robust code is based on multiplicative inverse in finite field. In the second robust code construction the redundancy part is a cube of information part. Also, this paper investigates the characteristics of proposed robust and linear codes.

Keywords: robust code, linear code, wavelet decomposition, scaling function, error masking probability

Procedia PDF Downloads 474

Authors: Reza Rezaeipour Honarmandzad

Abstract:

This paper introduces an aircraft cable fault detection and location method in light of TFDR keeping in mind the end goal to recognize the intermittent faults adequately and to adapt to the serial and after-connector issues being hard to be distinguished in time domain reflection. In this strategy, the correlation function of reflected and reference signal is used to recognize and find the airplane fault as per the qualities of reflected and reference signal in time-frequency domain, so the hit rate of distinguishing and finding intermittent faults can be enhanced adequately. In the work process, the reflected signal is interfered by the noise and false caution happens frequently, so the threshold de-noising technique in light of wavelet decomposition is used to diminish the noise interference and lessen the shortcoming alert rate. At that point the time-frequency cross connection capacity of the reference signal and the reflected signal based on Wigner-Ville appropriation is figured so as to find the issue position. Finally, LabVIEW is connected to execute operation and control interface, the primary capacity of which is to connect and control MATLAB and LABSQL. Using the solid computing capacity and the bottomless capacity library of MATLAB, the signal processing turn to be effortlessly acknowledged, in addition LabVIEW help the framework to be more dependable and upgraded effectively.

Keywords: aircraft cable, fault location, TFDR, LabVIEW

Procedia PDF Downloads 460

Authors: Zhaopeng Xuan, Yuan Bian, C. Cailleaux, Jing Qin, S. Traore

Abstract:

Traditional software engineering allows engineers to propose to their clients multiple specialized software distributions assembled from a shared set of software assets. The management of these assets however requires a trade-off between client satisfaction and software engineering process. Clients have more and more difficult to find a distribution or components based on their needs from all of distributed repositories. This paper proposes a software engineering for a user-driven software product line in which engineers define a feature model but users drive the actual software distribution on demand. This approach makes the user become final actor as a release manager in software engineering process, increasing user product satisfaction and simplifying user operations to find required components. In addition, it provides a way for engineers to manage and assembly large software families. As a proof of concept, a user-driven software product line is implemented for eclipse, an integrated development environment. An eclipse feature model is defined, which is exposed to users on a cloud-based built platform from which clients can download individualized Eclipse distributions.

Keywords: software product line, model-driven development, reverse engineering and refactoring, agile method

Procedia PDF Downloads 414

Authors: Sara Vora (Hoxha)

Abstract:

An essential feature of any international lawsuit is the ability of the parties to pick the law that would apply in the event of a tort claim. This option to choose the law to use in tort cases is based on Article 14 and 4/3 of the Rome II Regulation. The purpose of this article is to examine the boundaries of this freedom, as well as its relevance in international legal disputes. The article opens with a brief introduction to the basics of tort law. After a short introduction, the article demonstrates why Article 14 and 4/3 of the Rome II Regulation are so crucial to the right to select appropriate law in tort cases. The notion of the right to select the law to use in tort cases is examined, along with its breadth and possible restrictions. The article presents case studies to demonstrate how the right to select relevant law in tort might be put into practise. Case results and the judges' rationales for their rulings are examined. The possible influence of the right to select applicable law in tort on the process of harmonisation is also explored in this study. The results are summarised and the primary research question is addressed in the last section of the paper. In conclusion, the parties' ability to pick the law that rules their dispute via the freedom to choose relevant law in tort is a crucial feature of cross-border litigation. Despite certain restrictions, this freedom is nevertheless an important part of the legal structure that governs international conflicts.

Keywords: applicable law, tort, Rome II regulation, freedom to choose, cross-border litigation, harmonization of tort law

Procedia PDF Downloads 46

Authors: Delara Kazempour, Mashallah Abasi Dezfuli, Reza Javidan

Abstract:

Video compression used for channels with limited bandwidth and storage devices has limited storage capabilities. One of the most popular approaches in video compression is the usage of different transforms. Discrete cosine transform is one of the video compression methods that have some problems such as blocking, noising and high distortion inappropriate effect in compression ratio. wavelet transform is another approach is better than cosine transforms in balancing of compression and quality but the recognizing of curve curvature is so limit. Because of the importance of the compression and problems of the cosine and wavelet transforms, the contourlet transform is most popular in video compression. In the new proposed method, we used contourlet transform in video image compression. Contourlet transform can save details of the image better than the previous transforms because this transform is multi-scale and oriented. This transform can recognize discontinuity such as edges. In this approach we lost data less than previous approaches. Contourlet transform finds discrete space structure. This transform is useful for represented of two dimension smooth images. This transform, produces compressed images with high compression ratio along with texture and edge preservation. Finally, the results show that the majority of the images, the parameters of the mean square error and maximum signal-to-noise ratio of the new method based contourlet transform compared to wavelet transform are improved but in most of the images, the parameters of the mean square error and maximum signal-to-noise ratio in the cosine transform is better than the method based on contourlet transform.

Keywords: video compression, contourlet transform, discrete cosine transform, wavelet transform

Procedia PDF Downloads 421

Authors: Mawloud Mosbah, Bachir Boucheham

Abstract:

We present here the results for a comparative study of some techniques, available in the literature, related to the relevance feedback mechanism in the case of a short-term learning. Only one method among those considered here is belonging to the data mining field which is the K-Nearest Neighbours Algorithm (KNN) while the rest of the methods is related purely to the information retrieval field and they fall under the purview of the following three major axes: Shifting query, Feature Weighting and the optimization of the parameters of similarity metric. As a contribution, and in addition to the comparative purpose, we propose a new version of the KNN algorithm referred to as an incremental KNN which is distinct from the original version in the sense that besides the influence of the seeds, the rate of the actual target image is influenced also by the images already rated. The results presented here have been obtained after experiments conducted on the Wang database for one iteration and utilizing colour moments on the RGB space. This compact descriptor, Colour Moments, is adequate for the efficiency purposes needed in the case of interactive systems. The results obtained allow us to claim that the proposed algorithm proves good results; it even outperforms a wide range of techniques available in the literature.

Keywords: CBIR, category search, relevance feedback, query point movement, standard Rocchio’s formula, adaptive shifting query, feature weighting, original KNN, incremental KNN

Procedia PDF Downloads 266

Authors: Vimal O. Kumar, C. K. Muthukumaran, P. Rakesh

Abstract:

Liquid rocket engine (LRE) combustion chamber is subjected to pressure oscillation during the combustion process. The combustion noise (acoustic noise) is a broad band, small amplitude, high frequency component pressure oscillation. They constitute only a minor fraction ( < 1%) of the entire combustion process. However, this high frequency oscillation is huge concern during the design phase of LRE combustion chamber as it would cause catastrophic failure of the chamber. Depends on the chamber geometry, certain frequencies form standing wave pattern, and they resonate with high amplitude and are known as Eigen modes. These Eigen modes could cause failures unless it is suppressed to be within safe limits. These modes are categorized into radial, tangential, and azimuthal modes, and their structure inside the combustion chamber is of interest to the researchers. In the present proposal, experimental as well as numerical simulation will be performed to obtain the frequency-amplitude characteristics of the model combustion chamber for different baffle configuration. The main objective of this study is to find effect of baffle configuration that would provide better suppression of acoustic modes. The experimental study aims at measuring the frequency amplitude characteristics at certain points in the chamber wall. The experimental measurement will be also used for scheme used in numerical simulation. In addition to experiments, numerical simulation would provide detailed structure of the Eigenmodes exhibited and their level of suppression with the aid of different baffle configurations.

Keywords: baffle, instability, liquid rocket engine, pressure response of chamber

Procedia PDF Downloads 108

Authors: Farhad Alizadeh, Alireza Faregh Gharamaleki, Mojtaba Jalilzadeh, Houshang Gholami, Ali Akhoundzadeh

Abstract:

This study presented hybrid pre-processing approach along with a conceptual model to enhance the accuracy of river discharge prediction. In order to achieve this goal, Ensemble Empirical Mode Decomposition algorithm (EEMD), Discrete Wavelet Transform (DWT) and Mutual Information (MI) were employed as a hybrid pre-processing approach conjugated to Least Square Support Vector Machine (LSSVM). A conceptual strategy namely multi-station model was developed to forecast the Souris River discharge more accurately. The strategy used herein was capable of covering uncertainties and complexities of river discharge modeling. DWT and EEMD was coupled, and the feature selection was performed for decomposed sub-series using MI to be employed in multi-station model. In the proposed feature selection method, some useless sub-series were omitted to achieve better performance. Results approved efficiency of the proposed DWT-EEMD-MI approach to improve accuracy of multi-station modeling strategies.

Keywords: river stage-discharge process, LSSVM, discrete wavelet transform, Ensemble Empirical Decomposition Mode, multi-station modeling

Procedia PDF Downloads 160

Authors: Armin Nabaei, M. Omair Ahmad, M. N. S. Swamy

Abstract:

Many facial expression and emotion recognition methods in the traditional approaches of using LDA, PCA, and EBGM have been proposed. In recent years deep learning models have provided a unique platform addressing by automatically extracting the features for the detection of facial expression and emotions. However, deep networks require large training datasets to extract automatic features effectively. In this work, we propose an efficient emotion detection algorithm using face images when only small datasets are available for training. We design a deep network whose feature extraction capability is enhanced by utilizing several parallel modules between the input and output of the network, each focusing on the extraction of different types of coarse features with fined grained details to break the symmetry of produced information. In fact, we leverage long range dependencies, which is one of the main drawback of CNNs. We develop this work by introducing a Dynamic Soft-Margin SoftMax.The conventional SoftMax suffers from reaching to gold labels very soon, which take the model to over-fitting. Because it’s not able to determine adequately discriminant feature vectors for some variant class labels. We reduced the risk of over-fitting by using a dynamic shape of input tensor instead of static in SoftMax layer with specifying a desired Soft- Margin. In fact, it acts as a controller to how hard the model should work to push dissimilar embedding vectors apart. For the proposed Categorical Loss, by the objective of compacting the same class labels and separating different class labels in the normalized log domain.We select penalty for those predictions with high divergence from ground-truth labels.So, we shorten correct feature vectors and enlarge false prediction tensors, it means we assign more weights for those classes with conjunction to each other (namely, “hard labels to learn”). By doing this work, we constrain the model to generate more discriminate feature vectors for variant class labels. Finally, for the proposed optimizer, our focus is on solving weak convergence of Adam optimizer for a non-convex problem. Our noteworthy optimizer is working by an alternative updating gradient procedure with an exponential weighted moving average function for faster convergence and exploiting a weight decay method to help drastically reducing the learning rate near optima to reach the dominant local minimum. We demonstrate the superiority of our proposed work by surpassing the first rank of three widely used Facial Expression Recognition datasets with 93.30% on FER-2013, and 16% improvement compare to the first rank after 10 years, reaching to 90.73% on RAF-DB, and 100% k-fold average accuracy for CK+ dataset, and shown to provide a top performance to that provided by other networks, which require much larger training datasets.

Keywords: computer vision, facial expression recognition, machine learning, algorithms, depp learning, neural networks

Procedia PDF Downloads 58

Authors: Sven Borén, Lisiana Nurhadi, Henrik Ny

Abstract:

From a theoretical perspective, electric buses can be more sustainable and can be cheaper than fossil fuelled buses in city traffic. The authors have not found other studies based on actual urban public transport in Swedish winter climate. Further on, noise measurements from buses for the European market were found old. The aims of this follow-up study was therefore to test and possibly verify in a real-life environment how energy efficient and silent electric buses are, and then conclude on if electric buses are preferable to use in public transport. The Ebusco 2.0 electric bus, fitted with a 311 kWh battery pack, was used and the tests were carried out during November 2014-April 2015 in eight municipalities in the south of Sweden. Six tests took place in urban traffic and two took place in more of a rural traffic setting. The energy use for propulsion was measured via logging of the internal system in the bus and via an external charging meter. The average energy use turned out to be 8% less (0,96 kWh/km) than assumed in the earlier theoretical study. This rate allows for a 320 km range in public urban traffic. The interior of the bus was kept warm by a diesel heater (biodiesel will probably be used in a future operational traffic situation), which used 0,67 kWh/km in January. This verified that electric buses can be up to 25% cheaper when used in public transport in cities for about eight years. The noise was found to be lower, primarily during acceleration, than for buses with combustion engines in urban bus traffic. According to our surveys, most passengers and drivers appreciated the silent and comfortable ride and preferred electric buses rather than combustion engine buses. Bus operators and passenger transport executives were also positive to start using electric buses for public transport. The operators did however point out that procurement processes need to account for eventual risks regarding this new technology, along with personnel education. The study revealed that it is possible to establish a charging infrastructure for almost all studied bus lines. However, design of a charging infrastructure for each municipality requires further investigations, including electric grid capacity analysis, smart location of charging points, and tailored schedules to allow fast charging. In conclusion, electric buses proved to be a preferable alternative for all stakeholders involved in public bus transport in the studied municipalities. However, in order to electric buses to be a prominent support for sustainable development, they need to be charged either by stand-alone units or via an expansion of the electric grid, and the electricity should be made from new renewable sources.

Keywords: sustainability, electric, bus, noise, greencharge

Procedia PDF Downloads 325